Parameter estimations for super resolution based on the Laplacian Pyramid representation

Image enlargement with higher frequency components prediction can be called as super resolution. In some print or copy applications, arbitrary scale enlargement is necessary. For obtaining better enlargement results, we have proposed one arbitrary scale super resolution method based on the Laplacian Pyramid representation [5]. In this method there are two parameters in the higher frequency prediction processing. In fact, the exact relationship of them is very complex. To expound the meaning of these two parameters for arbitrary scale super resolution, in this paper we will do a mathematic analysis via the unit step signal. But we also point out that theoretical analysis maybe can't get the best effect for the natural image enlargement and in actual applications the experiential way should not be disregarded, too.